© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15898
    Prev
    Next
    INDEX
    Explanations

    Please look

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įä»ħåı¯ä»¥
    -0.21
    å¤ļä¹Ī
    -0.19
     ultimate
    -0.19
    à¸Ļาà¸Ļ
    -0.19
    ä¸įä»ħæĺ¯
    -0.19
    еб
    -0.18
    елÑı
    -0.18
     anthrop
    -0.18
    arme
    -0.18
    oire
    -0.17
    POSITIVE LOGITS
    æŁ¥çľĭ详æĥħ
    0.22
    åĬ¡å¿ħ
    0.19
    æŁ¥çľĭæĽ´å¤ļ
    0.19
    çļĦè¯Ŀ
    0.18
    ãģ§ãģįãģ¾ãģĽãĤĵ
    0.18
    楼ä¸ĭ
    0.17
    认è´Ń
    0.17
    解åĨ³æĸ¹æ¡Ī
    0.17
     Fle
    0.17
    itr
    0.17
    Activations Density 0.106%

    No Known Activations